GoogleGemini Transcribe
Gemini 3.5 Transcribe
Gemini 3.5 Transcribe converts recorded audio into text and word-level annotations.
What the release provides
It handles files up to one hour, recognizes more than 85 languages, and supports language switching, speaker diarization, word timestamps and custom vocabulary.Gemini 3.5 Transcribe official API documentation
How to use it well
Practical guidance. Review names and specialist terms against the recording. Treat speaker labels as inferred labels until verified. Keep timestamps attached to corrected text so a transcript can still link a statement to its audio evidence.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Access | API |
| Model identifiers | gemini-3.5-transcribe |